Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Features
Speaker Deck
PRO
Sign in
Sign up for free
Search
Search
Harnessing the power of AI in IntelliJ IDEA
Search
Sponsored
·
Ship Features Fearlessly
Turn features on and off without deploys. Used by thousands of Ruby developers.
→
Anton Arhipov
March 26, 2025
Programming
1
220
Harnessing the power of AI in IntelliJ IDEA
Anton Arhipov
March 26, 2025
Tweet
Share
More Decks by Anton Arhipov
See All by Anton Arhipov
Strengthening Immutability in Kotlin. A Glimpse into Valhalla
antonarhipov
2
72
Kotlin—the New and Noteworthy in 2.2
antonarhipov
1
31
Levels of AI-assisted programming
antonarhipov
0
110
Devoxx France 2024. Kotlin - the new and noteworthy
antonarhipov
2
90
VirtualJUG: Kotlin 2.0 and beyond
antonarhipov
1
150
Kotlin 2.1: Language Updates
antonarhipov
3
190
Devoxx Belgium 2024 - Kotlin 2.0 and beyond
antonarhipov
2
190
Data Analysis with Kotlin Notebook, DataFrame, and Kandy
antonarhipov
1
130
Kotlin 2.0 and Beyond
antonarhipov
2
290
Other Decks in Programming
See All in Programming
Symfony + NelmioApiDocBundle を使った スキーマ駆動開発 / Schema Driven Development with NelmioApiDocBundle
okashoi
0
170
[PHPerKaigi 2026]PHPerKaigi2025の企画CodeGolfが最高すぎて社内で内製して半年運営して得た内製と運営の知見
ikezoemakoto
0
150
RubyとGoでゼロから作る証券システム: 高信頼性が求められるシステムのコードの外側にある設計と運用のリアル
free_world21
0
310
社内規程RAGの精度を73.3% → 100%に改善した話
oharu121
13
8.2k
GoのDB アクセスにおける 「型安全」と「柔軟性」の両立 - Bob という選択肢
tak848
0
220
モックわからないマン卒業記 ~振る舞いを起点に見直した、フロントエンドテストにおけるモックの使いどころ~
tasukuwatanabe
3
400
「やめとこ」がなくなった — 1月にZennを始めて22本書いた AI共創開発のリアル
atani14
0
400
How to stabilize UI tests using XCTest
akkeylab
0
130
それはエンジニアリングの糧である:AI開発のためにAIのOSSを開発する現場より / It serves as fuel for engineering: insights from the field of developing open-source AI for AI development.
nrslib
0
260
PHPで TLSのプロトコルを実装してみる
higaki_program
0
200
Codex の「自走力」を高める
yorifuji
0
1.2k
コーディングルールの鮮度を保ちたい / keep-fresh-go-internal-conventions
handlename
0
210
Featured
See All Featured
JAMstack: Web Apps at Ludicrous Speed - All Things Open 2022
reverentgeek
1
390
Future Trends and Review - Lecture 12 - Web Technologies (1019888BNR)
signer
PRO
0
3.3k
Performance Is Good for Brains [We Love Speed 2024]
tammyeverts
12
1.5k
StorybookのUI Testing Handbookを読んだ
zakiyama
31
6.6k
個人開発の失敗を避けるイケてる考え方 / tips for indie hackers
panda_program
122
21k
CoffeeScript is Beautiful & I Never Want to Write Plain JavaScript Again
sstephenson
162
16k
AI Search: Where Are We & What Can We Do About It?
aleyda
0
7.1k
Responsive Adventures: Dirty Tricks From The Dark Corners of Front-End
smashingmag
254
22k
Imperfection Machines: The Place of Print at Facebook
scottboms
269
14k
Statistics for Hackers
jakevdp
799
230k
Paper Plane (Part 1)
katiecoart
PRO
0
5.7k
The MySQL Ecosystem @ GitHub 2015
samlambert
251
13k
Transcript
Harnessing the power of AI in Intell iJ IDEA
None
None
Full-line code completion Minimal assistance. Doesn't get in a way.
Can accept word-by- word with Alt + ->
None
As a result, completion provides a multi-line snippet of code
The comment act as a prompt, adding the information to the context
The snippets of code can be accepted line- by line
.
The snippets of code can be accepted line- by line
. ... or word-by-word
None
inline code generation
Specify additional requirements
With AI actions, we can generate more code. For instance,
generate unit tests.
AI assistant will trigger the workflow to generate unit tests
You still have to execute the tests, verify results, etc
You still have to execute the tests, verify results, etc
You are in control!
None
A more complex change spanning multiple par t s of
the application
The workflow makes changes to multiple files and creates new
files
The workflow makes changes to multiple files and creates new
files You still have to review the changes, accept of decline, run tests, review code .
The workflow makes changes to multiple files and creates new
files You are in control! You still have to review the changes, accept of decline, run tests, review code .
None
None
None
Junie writes code, writes tests, verifies new code, etc .
It's an "autopilot" for writing code under your supervision
Automatically executes tests. Iterates on the task
None
The level of control Max Min
The level of control Max Min You can have various
levels of control over the process To get the most out of the agentic mode, you will need the relax the control. Then you can move faster!
None
None
None
None
None
https://speakerdeck.com/antonarhipov @antonarhipov https://github.com/antonarhipov